{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TE3PQ7FXEB6MH2TVHVMHOB6M5H","short_pith_number":"pith:TE3PQ7FX","schema_version":"1.0","canonical_sha256":"9936f87cb7207cc3ea753d587707cce9dfb2576c2c35f89a077fb2022a1517ed","source":{"kind":"arxiv","id":"2409.04388","version":5},"attestation_state":"computed","paper":{"title":"Question-Answering Dense Video Events","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Angela Yao, Hangyu Qin, Junbin Xiao","submitted_at":"2024-09-06T16:27:52Z","abstract_excerpt":"This paper presents question-answering on dense video events, a novel task that answers and grounds dense-event questions in long videos, thus challenging MLLMs to faithfully comprehend and reason about multiple events over extended periods of time. To facilitate the study, we construct DeVE-QA -- a dataset featuring 78K questions about 26K events on 10.6K long videos. Our benchmarking shows that state-of-the-art MLLMs struggle on DeVE-QA. For improvement, we propose DeVi, a novel training-free MLLM approach that highlights a hierarchical captioning module, a temporal event memory module, and "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.04388","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-06T16:27:52Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"d40e7812a683057421acc66303cdfb9c7148519d698af625f4c12504db839ebc","abstract_canon_sha256":"e41d5510d0653b1887d6dd13b32a3fbb585d810a07c7ba58803a3f7f0eb09c1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:51.818409Z","signature_b64":"80hGTNOUVxspS5k/zxoj4tZYZkQlkKx2QWRtdRzxCttGirkxnHXHBFm/ibJfMtJty9dsknizvBjV/YWBPP1jDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9936f87cb7207cc3ea753d587707cce9dfb2576c2c35f89a077fb2022a1517ed","last_reissued_at":"2026-07-05T11:03:51.817753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:51.817753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Question-Answering Dense Video Events","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Angela Yao, Hangyu Qin, Junbin Xiao","submitted_at":"2024-09-06T16:27:52Z","abstract_excerpt":"This paper presents question-answering on dense video events, a novel task that answers and grounds dense-event questions in long videos, thus challenging MLLMs to faithfully comprehend and reason about multiple events over extended periods of time. To facilitate the study, we construct DeVE-QA -- a dataset featuring 78K questions about 26K events on 10.6K long videos. Our benchmarking shows that state-of-the-art MLLMs struggle on DeVE-QA. For improvement, we propose DeVi, a novel training-free MLLM approach that highlights a hierarchical captioning module, a temporal event memory module, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04388","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.04388/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.04388","created_at":"2026-07-05T11:03:51.817819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.04388v5","created_at":"2026-07-05T11:03:51.817819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04388","created_at":"2026-07-05T11:03:51.817819+00:00"},{"alias_kind":"pith_short_12","alias_value":"TE3PQ7FXEB6M","created_at":"2026-07-05T11:03:51.817819+00:00"},{"alias_kind":"pith_short_16","alias_value":"TE3PQ7FXEB6MH2TV","created_at":"2026-07-05T11:03:51.817819+00:00"},{"alias_kind":"pith_short_8","alias_value":"TE3PQ7FX","created_at":"2026-07-05T11:03:51.817819+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TE3PQ7FXEB6MH2TVHVMHOB6M5H","json":"https://pith.science/pith/TE3PQ7FXEB6MH2TVHVMHOB6M5H.json","graph_json":"https://pith.science/api/pith-number/TE3PQ7FXEB6MH2TVHVMHOB6M5H/graph.json","events_json":"https://pith.science/api/pith-number/TE3PQ7FXEB6MH2TVHVMHOB6M5H/events.json","paper":"https://pith.science/paper/TE3PQ7FX"},"agent_actions":{"view_html":"https://pith.science/pith/TE3PQ7FXEB6MH2TVHVMHOB6M5H","download_json":"https://pith.science/pith/TE3PQ7FXEB6MH2TVHVMHOB6M5H.json","view_paper":"https://pith.science/paper/TE3PQ7FX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.04388&json=true","fetch_graph":"https://pith.science/api/pith-number/TE3PQ7FXEB6MH2TVHVMHOB6M5H/graph.json","fetch_events":"https://pith.science/api/pith-number/TE3PQ7FXEB6MH2TVHVMHOB6M5H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TE3PQ7FXEB6MH2TVHVMHOB6M5H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TE3PQ7FXEB6MH2TVHVMHOB6M5H/action/storage_attestation","attest_author":"https://pith.science/pith/TE3PQ7FXEB6MH2TVHVMHOB6M5H/action/author_attestation","sign_citation":"https://pith.science/pith/TE3PQ7FXEB6MH2TVHVMHOB6M5H/action/citation_signature","submit_replication":"https://pith.science/pith/TE3PQ7FXEB6MH2TVHVMHOB6M5H/action/replication_record"}},"created_at":"2026-07-05T11:03:51.817819+00:00","updated_at":"2026-07-05T11:03:51.817819+00:00"}